vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Can't load any gemma 2 model
- [Kernel] Add prefix-caching support for phi-3-small-8k/128k model triton kernel
- [Performance]: V0.6.0 version of the model, benchmarking found that the number of successful responses accounted for half of the number of requests, which is why
- [CI/Build]: Add Bandit security check to workflow
- [Performance]: INFO 09-11 12:41:50 spec_decode_worker.py:790] SpecDecodeWorker scoring_time_ms is slow
- [Feature]: Add ray cluster start logic to vllm container for multi host inference with leaderworkerset
- [Bugfix] Reenable LRU cache on Outlines' guide getters
- [Misc] Benchmark for awq_triton kernels
- [RFC]: Pinned Caching with Automatic Prefix Caching (Related to Anthropic Prompt Caching API)
- [Core] feat: support pinned caching with prefix caching
- Docs
- Python not yet supported